Loading [MathJax]/extensions/MathZoom.js
Preventing Spoofing Threats in IoT: Machine Learning Approaches for Intrusion Detection | IEEE Conference Publication | IEEE Xplore

Preventing Spoofing Threats in IoT: Machine Learning Approaches for Intrusion Detection


Abstract:

The safety and reliability of Internet of Things (IoT) networks have to be guaranteed because of the quick spread of IoT devices. Significant risks to IoT deployments com...Show More

Abstract:

The safety and reliability of Internet of Things (IoT) networks have to be guaranteed because of the quick spread of IoT devices. Significant risks to IoT deployments come from spoofing attacks, in which malevolent actors pretend to be trustworthy equipment to obtain illicit entry or interfere with normal operations. Utilizing the rich data supplied by an IoT intrusion detection dataset, this paper suggests a Machine Learning (ML)-based method for spotting spoofing attacks in IoT networks. In particular, investigate how well many ML algorithms such as Random Forests (RF), Naive Bayes (NB), Logistic Regression (LR), and Support Vector Machines (SVM) identify spoofing occurrences. Train and assess classifiers using supervised learning techniques on the IoT intrusion detection dataset, which includes various transmission patterns and instances of attack. After extensive testing and analysis, determine how well each algorithm performs in terms of F1-scoring, recall, precision, and detection accuracy. The findings demonstrate how effective ML techniques are in spotting spoofing attacks in IoT environments and highlight the potential of NB, LR, SVM, and RF as helpful tools for enhancing the safety posture of IoT deployments. These results provide useful information to cybersecurity experts and researchers working to lessen the risks of spoofing attacks in the IoT domain, as well as aiding in developing Intrusion Detection Systems (IDS) for IoT environments.
Date of Conference: 27-28 July 2024
Date Added to IEEE Xplore: 29 October 2024
ISBN Information:
Conference Location: Gwalior, India

References

References is not available for this document.